원문정보
초록
영어
This paper presents a novel approach to recognize person name in Uyghur corpus. The Recognition of a person name for Uyghur using Naive Bayes Classifier is a challenging task in intelligent computing. Uyghur person name recognition (UPNR) aims at classifying each word in a document into predefined target label (person name or others) in a linear and non-linear fashion. Some language specific rules are added to recognize person names. Moreover, some gazetteers and context patterns are added to increase its performance as it is observed that identification of rules and context patterns requires language-based knowledge to make the work better. We have used required lexical databases to prepare rules and identify the context patterns for Uyghur. Experimental results show that our approach achieves higher accuracy than previous approaches.
목차
1. Introduction
2. The Uyghur Text Corpus
3. Naïve Bayes Classifier
4. Training Data
4.1. Features
4.2. Suffix and Prefix
4.3. Stem of Word
4.4. The Algorithm
5. Experimental Results and Evaluations
6. Conclusions
References